import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

from plotly.offline import iplot
import plotly as py
import plotly.tools as tls

import cufflinks as cf

import plotly.express as px

import pandas_profiling as pf

py.offline.init_notebook_mode(connected=True)
cf.go_offline()

black_friday_df = pd.read_csv("blackFriday_train.csv")
black_friday_df[:20]

	User_ID	Product_ID	Gender	Age	Occupation	City_Category	Stay_In_Current_City_Years	Marital_Status	Product_Category_1	Product_Category_2	Product_Category_3	Purchase
0	1000001	P00069042	F	0-17	10	A	2	0	3	NaN	NaN	8370
1	1000001	P00248942	F	0-17	10	A	2	0	1	6.0	14.0	15200
2	1000001	P00087842	F	0-17	10	A	2	0	12	NaN	NaN	1422
3	1000001	P00085442	F	0-17	10	A	2	0	12	14.0	NaN	1057
4	1000002	P00285442	M	55+	16	C	4+	0	8	NaN	NaN	7969
5	1000003	P00193542	M	26-35	15	A	3	0	1	2.0	NaN	15227
6	1000004	P00184942	M	46-50	7	B	2	1	1	8.0	17.0	19215
7	1000004	P00346142	M	46-50	7	B	2	1	1	15.0	NaN	15854
8	1000004	P0097242	M	46-50	7	B	2	1	1	16.0	NaN	15686
9	1000005	P00274942	M	26-35	20	A	1	1	8	NaN	NaN	7871
10	1000005	P00251242	M	26-35	20	A	1	1	5	11.0	NaN	5254
11	1000005	P00014542	M	26-35	20	A	1	1	8	NaN	NaN	3957
12	1000005	P00031342	M	26-35	20	A	1	1	8	NaN	NaN	6073
13	1000005	P00145042	M	26-35	20	A	1	1	1	2.0	5.0	15665
14	1000006	P00231342	F	51-55	9	A	1	0	5	8.0	14.0	5378
15	1000006	P00190242	F	51-55	9	A	1	0	4	5.0	NaN	2079
16	1000006	P0096642	F	51-55	9	A	1	0	2	3.0	4.0	13055
17	1000006	P00058442	F	51-55	9	A	1	0	5	14.0	NaN	8851
18	1000007	P00036842	M	36-45	1	B	1	1	1	14.0	16.0	11788
19	1000008	P00249542	M	26-35	12	C	4+	1	1	5.0	15.0	19614

profile = pf.ProfileReport(df=black_friday_df,explorative=True)
profile.to_file(output_file="Profiling_report.html")

/opt/miniconda3/envs/intel/lib/python3.7/site-packages/scipy/stats/stats.py:4812: RuntimeWarning:

overflow encountered in long_scalars

profile

Most of the purchaser in terms of Gender

They are Males

Most of the purchaser's age

It is 26-35

Most of the persons have 17th type of occupation

fig = px.pie(pd.DataFrame(black_friday_df['Occupation']),values='Occupation',names='Occupation')
fig.show()

Most of the person belonging to B type city

Most of the buyers are unmarried

Filling NaN values in Product Category 2 and 3 with highest frequency

black_friday_df['Product_Category_2'] = black_friday_df['Product_Category_2'].fillna(black_friday_df['Product_Category_2'].mode()[0])

black_friday_df['Product_Category_3'] = black_friday_df['Product_Category_3'].fillna(black_friday_df['Product_Category_3'].mode()[0])

black_friday_df[['Product_Category_1']][:50].iplot()

black_friday_df[['Product_Category_2']][:50].iplot()

black_friday_df[['Product_Category_3']][:50].iplot()

Product 1 is purchased in pair of 5 at maximum

black_friday_df[['Product_Category_1']].iplot(kind='hist')

Product 2 is purchased in pair of 8 at maximum

black_friday_df[['Product_Category_2']].iplot(kind='hist')

Product 3 is purchased in pair of 16 at maximum

black_friday_df[['Product_Category_3']].iplot(kind='hist')

black_friday_df[['Product_Category_1','Product_Category_2','Product_Category_3']].describe()

	Product_Category_1	Product_Category_2	Product_Category_3
count	550068.000000	550068.000000	550068.000000
mean	5.404270	9.260768	14.989567
std	3.936211	4.294093	2.739846
min	1.000000	2.000000	3.000000
25%	1.000000	8.000000	16.000000
50%	5.000000	8.000000	16.000000
75%	8.000000	14.000000	16.000000
max	20.000000	18.000000	18.000000

Averagely bought product

On an average product 2 was bought most

black_friday_df[['Product_Category_1','Product_Category_2','Product_Category_3']].iplot(kind='box')

import numpy as np

li = []
for i in range(0,black_friday_df.shape[0]):
    temp = black_friday_df.iloc[i,-4:-1]
    li.append(np.argmax(temp))

black_friday_df[:20]

	User_ID	Product_ID	Gender	Age	Occupation	City_Category	Stay_In_Current_City_Years	Marital_Status	Product_Category_1	Product_Category_2	Product_Category_3	Purchase
0	1000001	P00069042	F	0-17	10	A	2	0	3	8.0	16.0	8370
1	1000001	P00248942	F	0-17	10	A	2	0	1	6.0	14.0	15200
2	1000001	P00087842	F	0-17	10	A	2	0	12	8.0	16.0	1422
3	1000001	P00085442	F	0-17	10	A	2	0	12	14.0	16.0	1057
4	1000002	P00285442	M	55+	16	C	4+	0	8	8.0	16.0	7969
5	1000003	P00193542	M	26-35	15	A	3	0	1	2.0	16.0	15227
6	1000004	P00184942	M	46-50	7	B	2	1	1	8.0	17.0	19215
7	1000004	P00346142	M	46-50	7	B	2	1	1	15.0	16.0	15854
8	1000004	P0097242	M	46-50	7	B	2	1	1	16.0	16.0	15686
9	1000005	P00274942	M	26-35	20	A	1	1	8	8.0	16.0	7871
10	1000005	P00251242	M	26-35	20	A	1	1	5	11.0	16.0	5254
11	1000005	P00014542	M	26-35	20	A	1	1	8	8.0	16.0	3957
12	1000005	P00031342	M	26-35	20	A	1	1	8	8.0	16.0	6073
13	1000005	P00145042	M	26-35	20	A	1	1	1	2.0	5.0	15665
14	1000006	P00231342	F	51-55	9	A	1	0	5	8.0	14.0	5378
15	1000006	P00190242	F	51-55	9	A	1	0	4	5.0	16.0	2079
16	1000006	P0096642	F	51-55	9	A	1	0	2	3.0	4.0	13055
17	1000006	P00058442	F	51-55	9	A	1	0	5	14.0	16.0	8851
18	1000007	P00036842	M	36-45	1	B	1	1	1	14.0	16.0	11788
19	1000008	P00249542	M	26-35	12	C	4+	1	1	5.0	15.0	19614

black_friday_df['Max_Purchased_prd_type'] = li

black_friday_df_gender_purchase = black_friday_df[['Gender','Max_Purchased_prd_type']]

black_friday_df_gender_purchase_F = black_friday_df_gender_purchase[black_friday_df_gender_purchase['Gender'] == 'F']

black_friday_df_gender_purchase_F['Max_Purchased_prd_type'].value_counts().iplot(kind='bar')

black_friday_df_gender_purchase_M = black_friday_df_gender_purchase[black_friday_df_gender_purchase['Gender'] == 'M']

black_friday_df_gender_purchase_M['Max_Purchased_prd_type'].value_counts().iplot(kind='bar')

black_friday_df[['Age','Max_Purchased_prd_type']].groupby('Age').agg(pd.Series.mode).iplot(kind='bar')

Purchase capacity of Married / Unmarried Person based on different city

As all the plots are very same, it is difficult to identify difference. Hence, no analysis can be obtained

px.violin(x=black_friday_df['City_Category'],y=black_friday_df["Purchase"],color=black_friday_df['Marital_Status'])

px.violin(x=black_friday_df['City_Category'],y=black_friday_df["Purchase"],color=black_friday_df['Gender'])

px.violin(x=black_friday_df['City_Category'],y=black_friday_df["Purchase"],color=black_friday_df['Age'])

Purchasing power of different age people and categorized by Gender

Purchasing of goods of each range of age are almost equal. We can conclude that the percentage of purchasing goods of men over women is higher.

px.box(x=black_friday_df['Age'],y=black_friday_df["Purchase"],color=black_friday_df['Gender'])

black_friday_df['Purchase'].iplot(kind='distplot',mean=black_friday_df['Purchase'].mean())

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-145-d7a12d1a7ce8> in <module>
----> 1 black_friday_df['Purchase'].iplot(kind='distplot',mean=black_friday_df['Purchase'].mean())

/opt/miniconda3/envs/intel/lib/python3.7/site-packages/cufflinks/plotlytools.py in _iplot(self, kind, data, layout, filename, sharing, title, xTitle, yTitle, zTitle, theme, colors, colorscale, fill, width, dash, mode, interpolation, symbol, size, barmode, sortbars, bargap, bargroupgap, bins, histnorm, histfunc, orientation, boxpoints, annotations, keys, bestfit, bestfit_colors, mean, mean_colors, categories, x, y, z, text, gridcolor, zerolinecolor, margin, labels, values, secondary_y, secondary_y_title, subplots, shape, error_x, error_y, error_type, locations, lon, lat, asFrame, asDates, asFigure, asImage, dimensions, asPlot, asUrl, online, **kwargs)
   1104                                 hist_data=self.transpose().values
   1105                                 kw=check_kwargs(kwargs,FF_DISTPLOT)
-> 1106                                 group_labels=kw.pop('group_labels',self.columns)
   1107                                 if histnorm:
   1108                                         kw['histnorm']=histnorm

/opt/miniconda3/envs/intel/lib/python3.7/site-packages/pandas/core/generic.py in __getattr__(self, name)
   5485         ):
   5486             return self[name]
-> 5487         return object.__getattribute__(self, name)
   5488 
   5489     def __setattr__(self, name: str, value) -> None:

AttributeError: 'Series' object has no attribute 'columns'

import seaborn as sns

sns.set(rc={'figure.figsize':(11.7,8.27)})
sns.distplot(x=black_friday_df['Purchase'])

/opt/miniconda3/envs/intel/lib/python3.7/site-packages/seaborn/distributions.py:2551: FutureWarning:

`distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).

<AxesSubplot:ylabel='Density'>

black_friday_df['Purchase'].mean()

9263.968712959126

black_friday_df['Purchase'].median()

8047.0